summaryrefslogtreecommitdiffstats
path: root/net/mac80211/key.c
diff options
context:
space:
mode:
authorFelix Fietkau2019-03-18 12:00:58 +0100
committerJohannes Berg2019-04-08 13:31:31 +0200
commit2b4a66980217332d91ab1785e1750857d6d52bc8 (patch)
tree60e63e9c3911eb5a9993200886365a9deac37172 /net/mac80211/key.c
parentmac80211_hwsim: calculate if_combination.max_interfaces (diff)
downloadkernel-qcow2-linux-2b4a66980217332d91ab1785e1750857d6d52bc8.tar.gz
kernel-qcow2-linux-2b4a66980217332d91ab1785e1750857d6d52bc8.tar.xz
kernel-qcow2-linux-2b4a66980217332d91ab1785e1750857d6d52bc8.zip
mac80211: make ieee80211_schedule_txq schedule empty TXQs
Currently there is no way for the driver to signal to mac80211 that it should schedule a TXQ even if there are no packets on the mac80211 part of that queue. This is problematic if the driver has an internal retry queue to deal with software A-MPDU retry. This patch changes the behavior of ieee80211_schedule_txq to always schedule the queue, as its only user (ath9k) seems to expect such behavior already: it calls this function on tx status and on powersave wakeup whenever its internal retry queue is not empty. Also add an extra argument to ieee80211_return_txq to get the same behavior. This fixes an issue on ath9k where tx queues with packets to retry (and no new packets in mac80211) would not get serviced. Fixes: 89cea7493a346 ("ath9k: Switch to mac80211 TXQ scheduling and airtime APIs") Signed-off-by: Felix Fietkau <nbd@nbd.name> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Diffstat (limited to 'net/mac80211/key.c')
0 files changed, 0 insertions, 0 deletions